UNIX for Dummies Questions & Answers

#!/usr/bin/perl
# senhia83.pl

use strict;
use warnings;

my %group_first_line; # to save the first group encounter
my %group_values; # to save first group value encounter

# read every file line by line
while(<>) {
    chomp; # remove the ending newline if there
    # extract group and value
    my ($group, $value) = (split)[1,2];
    # if the group have not been seen yet create a record of 
    # first line and value
    if ( not exists $group_first_line{$group} ) {
        $group_first_line{$group} = $_;
        $group_values{$group} = $value;
        next; # jump to read line again
    }
    # if value does not match the first time, substitute it for missing
    if ($value ne $group_values{$group}) {
        $group_first_line{$group} =~ s/\s\w+?$/ missing/;
    }
}
# display the result
for my $group (keys %group_values) {
    print "$group_first_line{$group}\n";
}

perl senhia83.pl file

 
$ cat test3
name2 id1group1 value1
name4 id1group1 value2
name1 id2group1 value2
name2 id2group1 value2
name4 id2group1 value2
name1 id1group2 value1
name2 id1group2 value2

 
name4 id1group1 missing
name1 id2group1 value2
name2 id1group2 missing

 
name2 id1group1 missing
name1 id2group1 value2
name1 id1group2 missing

# extract group and value
    my ($group, $value) = (split)[1,2];

(split '\t')[1,2];

$group_first_line{$group} =~ s/\s\w+?$/\tmissing/;

$group_first_line{$group} =~ s/(\s)\w+?$/$1missing/;

#!/usr/bin/perl

use strict;
use warnings;

my %records;

while(<>) {
    chomp;
    
    my ($id, $group, $value) = split;
    
    if ( not exists $records{$group} ) {
        $records{$group} = [$id, $group, $value];
        next;
    }
    next if $records{$group}->[2] eq "missing";
    if ($records{$group}->[2] ne $value) {
        $records{$group}->[2] = "missing"} 
}

$,="\t";
for my $group (keys %records) {
    print "@{$records{$group}}\n"; 
}

cat group_test1
name2 id1group1 value1
name4 id1group1 value2
name1 id2group1 value2
name2 id2group1 value2
name4 id2group1 value2
name1 id1group2 value1
name2 id1group2 value2

awk 'NR==1{X=$2;S[$2]=$0;} {if( X != $2 ){if(!S[$2]){S[$2]=$0;}}} {if( X == $2){if( Y != $3 ){split(S[$2],D," ");D[3]="missing";S[$2]=D[1] OFS D[2] OFS D[3];}}} {X=$2;Y=$3} END{for(u in S){print S}}' group_test1

name1 id2group1 value2
name2 id1group1 missing
name1 id1group2 missing

cat group_test
name2 group1 value1
name1 group2 value1
name4 group1 value2
name2 group3 value2
name3 group3 value2
name2 group2 value2
name3 group2 value1
name1 group4 value1
name2 group4 value1
name1 group4 value1
name4 group4 value2
name2 group5 value2
name3 group5 value2
name2 group5 value2
name3 group5 value1
name3 group6 value1
name3 group6 value1

awk 'NR==1{X=$2;S[$2]=$0;} {if( X != $2 ){if(!S[$2]){S[$2]=$0;}}} {if( X == $2){if( Y != $3 ){split(S[$2],D," ");D[3]="missing";S[$2]=D[1] OFS D[2] OFS D[3];}}} {X=$2;Y=$3} END{for(u in S){print S}}' group_test

name2 group1 missing
name1 group2 missing
name2 group3 value2
name1 group4 missing
name2 group5 missing
name3 group6 value1

awk 'NR==1{
X=$2;S[$2]=$0;
}
        {if( X != $2 )
                {if(!S[$2])
                        {S[$2]=$0;}
                }
        }
{if( X == $2)
        {if( Y != $3 )
                {split(S[$2],D," ");
                D[3]="missing";S[$2]=D[1] OFS D[2] OFS D[3];
                }
        }
}
{X=$2;Y=$3}
END{
{for(u in S){print S[u]}}
}' group_test  ## Your input file name ##